The Influence of Experimental Design on the Detection of Performance Differences

We demonstrate the effect of sample and trial size on statistical outcomes for single-subject analyses ( SSA) and group analyses ( GA) for a frequently studied performance activity and common intervention. Fifty strides of walking data collected in two blocks of 25 trials for two shoe conditions were analyzed for samples of five, eight, 10, and 12 subjects and five, 10, 25, and 50 trials. SSA revealed a greater number of differences ( p <.05) than GA for all sample and trial sizes. Increasing sample size resulted in consistent increases in the number of differences for GA; differences for SSA were independent of sample size. Increasing trial size from five to 50 resulted in increased differences for SSA; GA were independent of trial size. Detecting significant differences in group designs is more dependent on the number of subjects, while SSA are more dependent on the number of trials.